Abstract
This research presents a scalable analytics framework using Data Envelopment Analysis (DEA) to support innovative, data-driven decision-making in the textile manufacturing sector, a key industry for economic development in South Asia. By applying both Constant Returns to Scale (CRS) and Variable Returns to Scale (VRS) models for inputs and outputs, the study evaluates the operational efficiency of 2 individual manufacturing lines, categorizing them into Efficient, Weakly Efficient, or Inefficient tiers. To guide strategic improvements, the Most Productive Scale Size (MPSS) model is employed to identify optimal scale sizes and returns to scale, enabling tailored recommendations for each group. This approach not only enhances performance at the line level but also contributes to broader organizational efficiency strategies. The proposed DEA framework is adaptable and can be extended to other manufacturing contexts. Future research directions include integrating longitudinal data and exploring the impact of emerging technologies on operational efficiency, further strengthening the role of analytics in strategic decision-making.
Recommended Citation
Wijayanayake, Annista and Silva, Manod De, "Designing Scalable DEA Based Analytics for Strategic
Efficiency Optimization in Textile Manufacturing" (2025). ACIS 2025 Proceedings. 45.
https://aisel.aisnet.org/acis2025/45